mlsanityData to 7 Oct 2026

Interpreting Representation Quality of DNNs for 3D Point Cloud Processing

arXiv 2111.03549 ↗First posted 5 Nov 2021cs.CV cs.AI cs.LGcited by 12

Not on the map. Why?

Abstract (arXiv)

In this paper, we evaluate the quality of knowledge representations encoded in deep neural networks (DNNs) for 3D point cloud processing. We propose a method to disentangle the overall model vulnerability into the sensitivity to the rotation, the translation, the scale, and local 3D structures. Besides, we also propose metrics to evaluate the spatial smoothness of encoding 3D structures, and the representation complexity of the DNN. Based on such analysis, experiments expose representation problems with classic DNNs, and explain the utility of the adversarial training.

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Builds on 41 of its 57 references that are in the map. First posted on arXiv 5 Nov 2021.

Builds on

41 of 57 references.

References · 41

  1. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
  2. 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
  3. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  4. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  5. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  6. 2015Learning Deep Features for Discriminative Localizationcited by 2,430
  7. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,348
  8. 2013Visualizing and Understanding Convolutional Networkscited by 2,278
  9. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  10. 2016Adversarial examples in the physical worldcited by 1,762
  11. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,202
  12. 2017Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networkscited by 936
29 more
  1. 2018PointCNN: Convolution On X-Transformed Pointscited by 764
  2. 2018PointConv: Deep Convolutional Networks on 3D Point Cloudscited by 656
  3. 2019Deep Hough Voting for 3D Object Detection in Point Cloudscited by 648
  4. 2017Interpretable Explanations of Black Boxes by Meaningful Perturbationcited by 611
  5. 2019RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Cloudscited by 584
  6. 2019PointFlow: 3D Point Cloud Generation with Continuous Normalizing Flowscited by 487
  7. 2014Understanding Deep Image Representations by Inverting Themcited by 399
  8. 2017Large-scale Point Cloud Semantic Segmentation with Superpoint Graphscited by 384
  9. 2019Relation-Shape Convolutional Neural Network for Point Cloud Analysiscited by 346
  10. 2019The many Shapley values for model explanationcited by 341
  11. 2015Understanding Neural Networks Through Deep Visualizationcited by 332
  12. 2019Deep Closest Point: Learning Representations for Point Cloud Registrationcited by 318
  13. 2018Consistent Individualized Feature Attribution for Tree Ensemblescited by 279
  14. 2018PU-Net: Point Cloud Upsampling Networkcited by 208
  15. 2014Object Detectors Emerge in Deep Scene CNNscited by 178
  16. 2015Inverting Visual Representations with Convolutional Networkscited by 168
  17. 2017SGPN: Similarity Group Proposal Network for 3D Point Cloud Instance Segmentationcited by 168
  18. 2021Revisiting Point Cloud Shape Classification with a Simple and Effective Baselinecited by 145
  19. 2019The Shapley Taylor Interaction Indexcited by 143
  20. 2019Explaining Deep Neural Networks with a Polynomial Time Algorithm for Shapley Values Approximationcited by 115
  21. 2018PointCloud Saliency Mapscited by 112
  22. 2020Shapley explainability on the data manifoldcited by 88
  23. 2019Interpolated Convolutional Networks for 3D Point Cloud Understandingcited by 86
  24. 2017Learning how to explain neural networks: PatternNet and PatternAttributioncited by 84
  25. 2020On Isometry Robustness of Deep 3D Point Cloud Models under Adversarial Attackscited by 46
  26. 2016GIFT: A Real-time and Scalable 3D Shape Search Enginecited by 31
  27. 20193D-Rotation-Equivariant Quaternion Neural Networkscited by 30
  28. 2020Technical Note: Game-Theoretic Interactions of Different Orderscited by 11
  29. 20173D Point Cloud Classification and Segmentation using 3D Modified Fisher Vector Representation for Convolutional Neural Networkscited by 8

Built on by

Cited by year

Citing papers per year: 2022: 3; 2023: 3; 2024: 1; 2025: 5.

12 papers.

  1. 2022Benchmarking Robustness of 3D Point Cloud Recognition Against Common Corruptionscited by 78
  2. 2023Does a Neural Network Really Encode Symbolic Concepts?cited by 27
  3. 2022Invariance-Aware Randomized Smoothing Certificatescited by 7
  4. 2023PointCert: Point Cloud Classification with Deterministic Certified Robustness Guaranteescited by 6
  5. 2023Risk-optimized Outlier Removal for Robust 3D Point Cloud Classificationcited by 6
  6. 2024Self-Supervised Multi-Frame Neural Scene Flowcited by 3
  7. 2025Adaptive Canonicalization with Application to Invariant Anisotropic Geometric Networkscited by 3
  8. 2025RECON: Robust symmetry discovery via Explicit Canonical Orientation Normalizationcited by 1
  9. 2025XAI for Point Cloud Data using Perturbations based on Meaningful Segmentationcited by 1
  10. 2025The Interaction Bottleneck of Deep Neural Networks: Discovery, Proof, and Modulationcited by 1
  11. 2022Explanation-based Counterfactual Retraining(XCR): A Calibration Method for Black-box Modelscited by 0
  12. 2025Desensitizing for Improving Corruption Robustness in Point Cloud Classification through Adversarial Trainingcited by 0